CN-122029571-A - Program, information processing apparatus, and information processing method

Abstract

The invention can efficiently acquire the data used for learning. The program causes a computer to function as a control unit that acquires, from a captured moving image obtained by capturing a character that performs a time-series operation, an expression, or a sound that is specified in script data, bone data, expression data, or sound data of the character in the captured moving image by referring to time information of each operation specified in the script data, and imparts attribute information to each of the acquired bone data, expression data, or sound data.

Inventors

• Xiaotian Changxiao

Assignees

• 索尼集团公司

Dates

Publication Date

20260512

Application Date

20240827

Priority Date

20231016

Claims (18)

1. 1. A program for causing a computer to function as a control unit that performs: Acquiring bone data, expression data, or sound data of a character in a captured moving image obtained by capturing the character in which a time-series action, expression, or sound is specified in script data, by referring to time information of each action specified in the script data, and Attribute information is given to each piece of bone data, each piece of expression data, or each piece of sound data obtained.
2. 2. The program according to claim 1, wherein, The control unit assigns information on an action, expression, or utterance included in the script data as the attribute information.
3. 3. The program according to claim 2, wherein, The control unit also gives information on the person as the attribute information.
4. 4. The program according to claim 1, wherein, The control unit: Generating a data set including at least any one of the bone data, the expression data, and the sound data to which the attribute information is given, and An image generation AI is constructed that learns the dataset.
5. 5. The program according to claim 1, wherein, The control unit: Generating a data set including at least any one of the bone data, the expression data, and the sound data to which the attribute information is given, and And carrying out additional learning on the data set by the learned model to construct an image generation AI.
6. 6. The program according to claim 1, wherein, The control unit: Generating a proper noun data set including at least the skeletal data, the expression data, or the sound data given the proper noun of the person as the attribute information, and An image generation AI is constructed that learns the proper noun dataset.
7. 7. The program according to claim 4, wherein, The control unit generates an AI image using the image generation AI based on text transmitted from an external device.
8. 8. The program according to claim 7, wherein, The text includes a designation of a person, The control unit generates an AI using the image in which the data set corresponding to the specified person is learned, and generates the AI image.
9. 9. The program according to claim 8, wherein, The control unit performs control to output feedback information for the specified person.
10. 10. The program according to claim 7, wherein, The control unit performs control to transmit the AI image to the external device.
11. 11. The program according to claim 7, wherein, The control unit generates an advertisement image for promoting the specified commodity as the AI image.
12. 12. The program according to claim 4, wherein, The control unit provides an image generation application program that generates an AI using the image to an external device.
13. 13. The program according to claim 4, wherein, The control unit provides an API (Application Programming Interface: application programming interface) for the image generation AI to an external device.
14. 14. The program according to claim 4, wherein, The control section regenerates the script data based on feedback related to an AI image generated by the image generation AI.
15. 15. The program according to claim 1, wherein, The control unit: generating a data set including the bone data, the expression data, and the sound data to which the attribute information is given; Constructing an image-generating AI that learns the dataset, and An AI image is generated using the image generation AI based on text transmitted from an external device.
16. 16. The program according to claim 15, wherein, The control section generates a singing moving image as the AI image.
17. 17. An information processing apparatus includes a control unit that performs: Acquiring bone data, expression data, or sound data of a character in a captured moving image obtained by capturing the character in which a time-series action, expression, or sound is specified in script data, by referring to time information of each action specified in the script data, and Attribute information is given to each piece of bone data, each piece of expression data, or each piece of sound data obtained.
18. 18. An information processing method, comprising the following processing by a processor: Acquiring bone data, expression data, or sound data of a character in a captured moving image obtained by capturing the character in which a time-series action, expression, or sound is specified in script data, by referring to time information of each action specified in the script data, and Attribute information is given to each piece of bone data, each piece of expression data, or each piece of sound data obtained.

Description

Program, information processing apparatus, and information processing method Technical Field The present disclosure relates to a program, an information processing apparatus, and an information processing method. Background In recent years, a technique of generating an image generation model by machine learning is expanding. In the case of performing machine learning, a lot of training data needs to be input to the generated model. For example, patent document 1 below discloses a technique for generating training data using a CG (Computer Graphics: computer graphics) model. In particular, it is disclosed to acquire an image based on parameters of a camera performing photographing or photographing conditions as training data. Patent document 1 International publication No. 2021/177324 However, the above-described patent document 1 relates to acquisition of an artificial image using a CG model, which still does not improve the case of collecting training data from a real person. Disclosure of Invention Accordingly, in the present disclosure, a program, an information processing apparatus, and an information processing method capable of efficiently acquiring data used for learning are proposed. According to the present disclosure, there is provided a program for causing a computer to function as a control unit that performs processing for acquiring, from a captured moving image obtained by capturing a character that performs a time-series prescribed action, expression, or sound in script data, each piece of bone data, each expression data, or each piece of sound data of the character in the captured moving image with reference to time information of each action prescribed in the script data, and for giving attribute information to each piece of the acquired bone data, each expression data, or each piece of sound data. Further, according to the present disclosure, there is provided an information processing apparatus including a control unit that acquires, from a captured moving image obtained by capturing a character that performs a time-series prescribed action, expression, or sound in script data, each piece of bone data, each expression data, or each piece of sound data of the character in the captured moving image with reference to time information of each action prescribed in the script data, and that imparts attribute information to each piece of the acquired bone data, each expression data, or each piece of sound data. Further, according to the present disclosure, there is provided an information processing method including a process of acquiring, from a captured moving image obtained by capturing a character that performs an action, an expression, or a sound that is specified in a time sequence in script data, bone data, expression data, or sound data of the character in the captured moving image with reference to time information of each action specified in the script data, and adding attribute information to each acquired bone data, expression data, or sound data, respectively. Drawings Fig. 1 is a diagram illustrating an outline of an AI advertisement generation service according to an embodiment of the present disclosure. Fig. 2 is a diagram showing the overall configuration of an information processing system 1 (AI advertisement generation system) according to an embodiment of the present disclosure. Fig. 3 is a block diagram showing an example of the structure of the server 20 according to the present embodiment. Fig. 4 is a sequence diagram showing an example of the flow of the image generation AI construction process in the information processing system 1 of the present embodiment. Fig. 5 is a view showing an example of a screen at the time of moving image capturing in the model terminal 10 according to the present embodiment. Fig. 6 is a diagram showing an example of a screen for transmitting moving image data according to the present embodiment. Fig. 7 is a diagram illustrating data analysis according to the present embodiment. Fig. 8 is a diagram showing an example of a data structure of bone data 401 with attribute information according to the present embodiment. Fig. 9 is a diagram showing an example of a data structure of expression data 402 with attribute information according to the present embodiment. Fig. 10 is a diagram showing an example of a data structure of audio data 403 with attribute information according to the present embodiment. Fig. 11 is a sequence diagram showing an example of the flow of the AI advertisement image generation process in the information processing system 1. Fig. 12 is a diagram showing a model selection screen 500 in the AI advertisement image generation request according to the present embodiment. Fig. 13 is a diagram showing an AI image generation screen 510 according to the present embodiment. Fig. 14 is a diagram showing an example of generation of an AI advertisement image based on a hint word according to the present embodiment. Fig. 15 is a flowcha